An MCP server that enables a supervising OpenAI Codex agent to delegate bounded implementation tasks to isolated worker threads with enforced file scopes and verification, optionally running in parallel git worktrees.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
mahadansar · Claimed
Source: Glama
Connect your repo and M8ven re-verifies it on the push itself. Without it we re-check verified listings about once a day, so a fix can sit unseen. Read-only, one click, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
BENCH_SUPERVISOR_MODELBENCH_TASK_TIMEOUTCODEX_HOMEOne table in ~/.codex/config.toml (or $/config.toml):LUNA_MODELgpt-5.6-luna Worker modelLUNA_NETWORK_ACCESSoff 1 allows workers network accessLUNA_SANDBOXworkspace-write Codex sandbox mode for workersLUNA_TIMEOUT_SECONDS1800 Wall-clock budget per delegated taskLUNA_VERIFY_TIMEOUT_SECONDSSOL_LUNA_ALLOWED_ROOTSConfine delegation to these directory treesSOL_LUNA_ALLOW_DIRTYbatch is refused (override with =1);SOL_LUNA_EVENTS"/path/to/codex-home/sol-luna-orchestrator.events.jsonl"SOL_LUNA_KEEP_WORKTREESonFailure always, never, or onFailureSOL_LUNA_LOG"/path/to/codex-home/sol-luna-orchestrator.log"SOL_LUNA_MAX_PARALLEL3 Concurrent workers; hard ceiling 8SOL_LUNA_SERVER_NAMEsol-luna-orchestrator Must match the name registered in CodexSOL_LUNA_SMOKE_SERVERSOL_LUNA_VERIFY_ALLOWExtra permitted executables, comma separatedSOL_LUNA_VERIFY_ENV_PASSTHROUGHoff 1 stops withholding credential-shaped env varsSOL_LUNA_VERIFY_MODEallowlist allowlist, off, or shell — see [Security](#security)SOL_LUNA_WORKTREE_LINKnode_modules Directories linked into each worktreeTERMTERM_PROGRAMWT_SESSIONTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
2/2 tools missing one or more hints — delegate_task (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); delegate_tasks (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
Only 0/2 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
5 child_process/subprocess calls in production code — runs shell commands (src/git.ts:37, src/smoke-cli.ts:64, src/verify.ts:173)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/mahadansar-sol-luna-orchestrator-1k52hj)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check